INDEX

Explanations

comparisons that emphasize something as being significantly greater or more complex than it appears

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PIO

-0.15

-0.14

ÑĢÐ¸Ð¹

-0.14

 Archive

-0.14

jo

-0.14

arking

-0.13

forth

-0.13

icken

-0.13

NX

-0.13

abeth

-0.13

POSITIVE LOGITS

mere

0.19

 mere

0.17

IDL

0.17

 beyond

0.16

/effects

0.16

 Blasio

0.15

eref

0.15

opis

0.15

mos

0.15

retch

0.15

Activations Density 0.082%

comparisons that emphasize something as being significantly greater or more complex than it appears

No Comments

No Known Activations